• The Journal of the Acoustical Society of Korea
• /
• v.15 no.5
• /
• pp.38-43
• /
• 1996

This paper compares the recognition performances of feature vectors known to be robust to the environmental noise. And, the speech subtraction technique is combined with the noise robust feature to get more performance enhancement. The experiments using SMC(Short time Modified Coherence) analysis, root cepstral analysis, LDA(Linear Discriminant Analysis), PLP(Perceptual Linear Prediction), RASTA(RelAtive SpecTrAl) processing are carried out. An isolated word recognition system is composed using semi-continuous HMM. Noisy environment experiments usign two types of noises:exhibition hall, computer room are carried out at 0, 10, 20dB SNRs. The experimental result shows that SMC and root based mel cepstrum(root_mel cepstrum) show 9.86% and 12.68% recognition enhancement at 10dB in compare to the LPCC(Linear Prediction Cepstral Coefficient). And when combined with spectral subtraction, mel cepstrum and root_mel cepstrum show 16.7% and 8.4% enhanced recognition rate of 94.91% and 94.28% at 10dB.

• The Journal of Society for e-Business Studies
• /
• v.25 no.1
• /
• pp.13-33
• /
• 2020

This study proposes a Korean sentimental analysis algorithm that utilizes a letter-unit embedding and convolutional neural networks. Sentimental analysis is a natural language processing technique for subjective data analysis, such as a person's attitude, opinion, and propensity, as shown in the text. Recently, Korean sentimental analysis research has been steadily increased. However, it has failed to use a general-purpose sentimental dictionary and has built-up and used its own sentimental dictionary in each field. The problem with this phenomenon is that it does not conform to the characteristics of Korean. In this study, we have developed a model for analyzing emotions by producing syllable vectors based on the onset, peak, and coda, excluding morphology analysis during the emotional analysis procedure. As a result, we were able to minimize the problem of word learning and the problem of unregistered words, and the accuracy of the model was 88%. The model is less influenced by the unstructured nature of the input data and allows for polarized classification according to the context of the text. We hope that through this developed model will be easier for non-experts who wish to perform Korean sentimental analysis.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.654-660
• /
• 2020

Through the output of brain waves during muscle operation, this paper checks whether it is possible to find characteristic vectors of brain waves that are capable of dividing left and right movements by extracting brain waves in specific areas of muscle signal output that include the motion of the left and right muscles or the will of the user within EEG signals, where uncertainties exist considerably. A typical surface EMG and noninvasive brain wave extraction method does not exist to distinguish whether the signal is a motion through the degree of ionization by internal neurotransmitter and the magnitude of electrical conductivity. In the case of joint and motor control through normal robot control systems or electrical signals, signals that can be controlled by the transmission and feedback control of specific signals can be identified. However, the human body lacks evidence to find the exact protocols between the brain and the muscles. Therefore, in this paper, efficiency is verified by utilizing the results of application of CSP (Common Spatial Pattern) filter to verify that the left-hand and right-hand signals can be extracted through brainwave analysis when the subject's behavior is performed. In addition, we propose ways to obtain data through experimental design for verification, to verify the change in results with or without filter application, and to increase the accuracy of the classification.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.2
• /
• pp.35-44
• /
• 2002

The translation and the rotation of camera occur global motion which affects all over the frame in video sequence. With the video sequences containing global motion, it is practically impossible to extract exact video objects and to calculate genuine object motions. Therefore, high compression ratio cannot be achieved due to the large motion vectors. This problem can be solved when the global motion compensated frames are used. The existing camera motion estimation methods for global motion compensation have a large amount of computations in common. In this paper, we propose a simple global motion estimation algorithm that consists of linear equations without any repetition. The algorithm uses information .of symmetric points in the frame of the video sequence. The discriminant conditions to distinguish regions belonging to distant view from foreground in the frame are presented. Only for the distant view satisfying the discriminant conditions, the linear equations for the panning, tilting, and zooming parameters are applied. From the experimental results using the MPEG test sequences, we can confirm that the proposed algorithm estimates correct global motion parameters. Moreover the real-time capability of the proposed technique can be applicable to many MPEG-4 and MPEG-7 related areas.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.5
• /
• pp.62-70
• /
• 2007

In this paper, the boost Power Factor Correction(PFC) technique for Direct Torque Control(DTC) of brushless DC motor drive in the constant torque region is implemented on a TMS320F2812DSP. Unlike conventional six-step PWM current control, by properly selecting the inverter voltage space vectors of the two-phase conduction mode from a simple look-up table at a predefined sampling time, the desired quasi-square wave current is obtained, therefore a much faster torque response is achieved compared to conventional current control. Furthermore, to eliminate the low-frequency torque oscillations caused by the non-ideal trapezoidal shape of the actual back-EMF waveform of the BLDC motor, a pre-stored back-EMF versus position look-up table is designed. The duty cycle of the boost converter is determined by a control algorithm based on the input voltage, output voltage which is the dc-link of the BLDC motor drive, and inductor current using average current control method with input voltage feed-forward compensation during each sampling period of the drive system. With the emergence of high-speed digital signal processors(DSPs), both PFC and simple DTC algorithms can be executed during a single sampling period of the BLDC motor drive. In the proposed method, since no PWM algorithm is required for DTC or BLDC motor drive, only one PWM output for the boost converter with 80 kHz switching frequency is used in a TMS320F2812 DSP. The validity and effectiveness of the proposed DTC of BLDC motor drive scheme with PFC are verified through the experimental results. The test results verify that the proposed PFC for DTC of BLDC motor drive improves power factor considerably from 0.77 to as close as 0.9997 with and without load conditions.

• Korean Journal of Environment and Ecology
• /
• v.30 no.4
• /
• pp.658-675
• /
• 2016

The environmental characteristics of the habitats, the population structures, ecological niche, life traits and the population demography are used as an essential informations to the effective conservation plans about the target species. We first confirmed a total of 37 populations through 12 years of investigation on the extents, and investigated the environmental factors of habitats and the population structures of the 25 cohorts in 12 regions among them. And, we investigated the population dynamics targeting at 8 cohorts in the population of Daegwanryeong-myeon, Pyeongchang-gun, Gangwon-do. Along with this, we conducted 4 years of cultivation experiments and how pollinators affect the success of reproduction. The results shows that the Paeonia obovata Maxim. was found in a relatively wide range of habitats. For the population structures of the 25 cohorts, there were considerable differences among cohorts, including a case which showed relative stable structure and an extreme case in which only adults were found. The factor that affected the population dynamics during the investigation was thought as a forest gap created in the tree layer. In the cultivation experiment, seedlings grew well in a less soil organic matter. The seed setting rate and the number of seeds generated by visiting pollinators were higher trends. In conclusion, to understand the distribution of the Paeonia obovata Maxim., there needs to be investigated on the other factors that are involved in dispersal factors other than environmental factors, and thus we suggest the necessity of the research on the dispersal vectors. The current Paeonia obovata Maxim. population was thought as a process of expansion after the rapid reduction of the extents in the past. For the effective conservation of the Paeonia obovata Maxim., an endangered plant, we recommend to understand the species through the spatio-temporal expansion, and maintain the health of the ecosystem based on it.

• Korean journal of applied entomology
• /
• v.14 no.2 s.23
• /
• pp.71-76
• /
• 1975

The study has been carried to find a proper site for seed potato production in Jeon Bug Province, Korea. Two fields, one at the alpine area (700-800 m sea level) in Muju county and the other at the plain area in Jeoniu, were chose for this study. Seed potatoes for the experiment were obtained from Alpine Experiment Station and from the traditional sources in Muju area. During the growing season the virus infection (Potato virus X,S,Y, and M) was detected by serolgical method. The average percent of virus infection on the original seed potatoes, which have been used as a seed source in Korea, was $50.5\%$, and the ratio of the infection for each of potato virus, Y, M and X was 34..87, 40.33, 41.00 and $87.10\%$, respectively. Infection percentage of virus at first year in Muju area was $11.7\%$ and those in Jeonju area was $18.95\%$. In case of potato virus Y, the most prevalent virus in Korea, lower Infection percentage $(6.45\%)$ was found in Muju area than in tile Jeonju area $(26.0\%)$ when the seed from Alpine Experiment Station was planted in both areas. The percentage of infected seed potato, Alpine Experiment Station$(41.75\%)$ was almost the same as those from the traditional sources in Muju $(42.17\%)$. The production of seed potato, however, was much better by the seeds from Alpine Experiment Station.

• Korean journal of applied entomology
• /
• v.52 no.1
• /
• pp.23-27
• /
• 2013

Investigations were conducted to prevent entrance of Bemisia tabaci (Gennadius) with very fine mesh nets. B. tabaci vectors tomato yellow leaf curl virus in tomatoes. B. tabaci could be completely prevented to penetrate into an 83 mesh net, though few of them passed the 60 mesh net. An independent 60 mesh net cage was built within one of the three interconnected common plastic greenhouse ($21.0{\times}18.3m$) in order to find its usefulness as a crop protection tool from insect pests. TYLCV infected tomato plants were not detected, though a few eggs of B. tabaci and mines of Liriomyza trifolii (Burgess) were detected locally at the entrance of the sliding door. There were practically no significant differences between treatments of nets and the conventional plant height, leaf length and width, number of floret clusters, sugar brix, and product yield. In viewpoints of commercialization, it could be considered highly prospectful to apply to the nets to glasshouses or other greenhouses in which the growing period of crops is long, if the nets were used in the openings of sides, ceilings, and entrances of the greenhouse. However, it might be necessary to take preventive measures for occurrences of insect pests living in soil, temporarily or permanently, as well as high humidity diseases.

• Research in Plant Disease
• /
• v.24 no.1
• /
• pp.9-25
• /
• 2018

Plant viruses cause significant yield losses and continuously threaten crop production, representing a serious threat to global food security. Studies on plant-virus interactions have contributed to increase our knowledge on plant immunity mechanism, providing new strategies for crop improvement. The prophylactic managements consist mainly following international legislations, eradication of infected plants, and application of pesticide to decrease the population of vectors. Hence, putting together the pieces of knowledge related to molecular plant immunity to viruses is critical for the control of virus disease in fields. Over the last several decades, the outstanding outcomes of extensive research have been achieved on comprehension of plant immunity to viruses. Although most dominant R genes have been used as natural resistance genes, recessive resistance genes have been deployed in several crops as another efficient strategy to control viruses. In addition, RNA interference also regulates plant immunity and contribute a very efficient antiviral system at the nucleic acid level. This review aims at describing virus disease on crops and summarizes current resistance mechanisms. Furthermore, we will discuss the current biotechnological approaches to control viral diseases and the future questions that are to be addressed to secure crop production against viruses.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.7
• /
• pp.692-700
• /
• 2012

Vibration intensity has been used to localize vibration source of a vibrating system. Not only that, vibration intensity has also been used for structural diagnostic in identifying crack and mounted stiffeners. To clearly identify the location of vibration source and understand the changes of energy transmission path, clear flow visualization is required. Most of previous works used vectors to indicate the magnitude and direction of emerging vibration energy and transmission paths. However, due to the large surface area of a plate like-structure, clear transmission paths cannot be achieved using vector visualization. This becomes an issue when detail vector flow at all locations of the whole plate surface is required. In this study, streamlines visualization is used to clearly indicate the power flow transmission path at all plate surface. By using streamlines representation, not only clear transmission paths are obtained, but also improves the vector visualization which helps us to understand the changes of the energy flow especially for stiffened plates. In this study, vibration intensity computation is firstly compared to previous work to validate the vibration intensity computation. To clearly show the power flow transmission paths, streamlines representation is shown. This representation overcomes the unclear vector direction especially for stiffened plates. Different pattern of energy transmission path can be observed using streamlines representation for stiffened and unstiffened plate. The complex streamlines pattern can also be observed at high resonance frequencies which is unclear by using vector representation.